A PRACTICAL APPROACH FOR THE INDIRECT PREDICTION OF STRUCTURAL FATIGUE FROM MEASURED FLIGHT PARAMETERS

The perceived benefits of permanent usage monitoring equipment in heli copters include savings in the cost of helicopter maintenance and a fa vourable impact on safety and fleet management. Unlike indirect fatigu e monitoring, direct load monitoring relies on a large number of senso rs which requires high operational and maintenance costs. In this pape r, a learning network has been developed, and during training sessions allowed to learn how to predict fatigue damage indirectly from flight parameters. Each training example consists of instantaneous fatigue d amage induced during a small time step, and flight parameters measured during the time step. The instantaneous damage values are evaluated t hrough a new approach called the progressive damage model. By consider ing the laws of aerodynamics and dynamics, the network combines the fl ight parameters in such a way that the resulting features can be mappe d into fatigue. About 10.5 flying hours of data were used to train the network. After training, the network was blind tested using flight pa rameters from 5.8 flying hours. The network was found to predict the f atigue damage of two rotating components indirectly from the flight pa rameters with accuracy better than the accuracy of a strain gauge syst em with 5 per cent measurement error.